Out-of-Domain Detection for Low-Resource Text Classification Tasks

Ming Tan, Yang Yu, Haoyu Wang, Dakuo Wang, Saloni Potdar, Shiyu Chang, Mo Yu


Abstract
Out-of-domain (OOD) detection for low-resource text classification is a realistic but understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training data, since in machine learning applications we observe that training data is often insufficient. In this work, we propose an OOD-resistant Prototypical Network to tackle this zero-shot OOD detection and few-shot ID classification task. Evaluations on real-world datasets show that the proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task, while maintaining a competitive performance on ID classification task.
Anthology ID:
D19-1364
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3566–3572
Language:
URL:
https://aclanthology.org/D19-1364
DOI:
10.18653/v1/D19-1364
Bibkey:
Cite (ACL):
Ming Tan, Yang Yu, Haoyu Wang, Dakuo Wang, Saloni Potdar, Shiyu Chang, and Mo Yu. 2019. Out-of-Domain Detection for Low-Resource Text Classification Tasks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3566–3572, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Out-of-Domain Detection for Low-Resource Text Classification Tasks (Tan et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1364.pdf
Code
 SLAD-ml/few-shot-ood